In-Vehicle Occupant Detection System Using mm-Wave Radar

This paper proposes a 77GHz millimeter wave radar-based rear occupant detection system in a vehicle. The major focus is detecting forgotten children in a vehicle's rear seats. The radar TX chirp signal configuration is selected to detect slight movements of people (like breathing). The radar RX IF signal is processed through 2D-FFT to build a two-dimension heat map. Then, the Constant False Alarm Detection (CFAR) algorithm is used for object detecting and a 2D cloud points image is obtained which can visualize the presence of people in the vehicle. Moreover, in the simulated vehicle environment experiment, our system can correctly identify if the vehicle is occupied or not in real time.